Biosafety Red Teaming Specialist
About The Position
The Intelligence and Investigations team at OpenAI seeks an expert in biological and chemical risks to lead red teaming efforts for biosafety and to help mature OpenAI’s bio bounty programs. This role involves shaping biology-relevant test plans, guiding external and internal engagements, ensuring testing is impactful, and translating findings into clear outcomes. The specialist will also play a critical role in driving bio bounty programs, including managing external researcher relationships, evolving challenge questions, reviewing submissions requiring biological subject-matter expertise, and scaling the program. The position requires broad and deep CBRN expertise, strong operational judgment or program management experience, and an adversarial mindset to understand how determined actors might misuse frontier AI systems and translate sensitive findings into actionable safety work.
Requirements
- A technical/scientific background with at least 8 years of technical CBRN experience.
- Deep subject-matter expertise in biosafety, biosecurity, biodefense, synthetic biology, microbiology, public health security, or adjacent CBRN domains, ideally with experience assessing dual-use biological risks.
- Experience with bio red teaming, threat modeling, misuse analysis, adversarial testing, intelligence analysis, or professional casework involving malicious actors or weaponization pathways.
- Strong operations and/or program management experience.
- Ability to prioritize ambiguous findings based on severity, feasibility, novelty, exposure, and potential real-world impact.
- Excellent judgment when handling sensitive biological information and can separate legitimate research from content that may enable harm.
- Ability to communicate complex technical and risk judgments in clear, grounded language for product, policy, safety, legal, and leadership audiences.
- Comfort working cross-functionally in fast-changing environments where the right answer may require both technical depth and pragmatic execution.
- Sufficient technical fluency to partner with data, engineering, and safety teams on signals, tooling, and scalable review processes.
- Resilience and thoughtfulness when engaging with sensitive, high-stakes material.
Nice To Haves
- Prior experience managing a bounty, vulnerability disclosure, external researcher, or expert review program.
- Experience with AI safety evaluations, model red teaming, or frontier model risk assessment.
- Familiarity with how advanced AI systems may affect biological safety, biosecurity, or CBRN risk.
Responsibilities
- Lead bio red teaming work from a domain perspective, including shaping evaluation questions, scenarios, and success criteria for biology-relevant misuse pathways.
- Review and pressure-test bio red teaming outputs, assess report quality, and help translate findings into concise risk calls and recommended next steps.
- Identify new red teaming engagements or external expert collaborations that would improve OpenAI's visibility into biological and overall CBRN misuse risks.
- Bring an adversarial mindset to assess how malicious actors could attempt to misuse model capabilities across planning, protocol design, procurement, troubleshooting, and operationalization.
- Directly manage Bio Bounty program strategy and maturity, including challenge-question lifecycle, expert researcher pipeline, submission review standards, and program health.
- Partner with operations owners on program execution while providing subject-matter review where biological expertise is required.
- Review Bio Bounty applications and invite known experts when appropriate to strengthen the researcher pool.
- Lead final biological-risk review on eligible submissions before awards, including severity, impact, novelty, and mitigation.
- Lead cross-functional efforts with Preparedness, Safety Systems, Policy, Legal, and other teams to turn high-quality findings into concrete follow-up work.
- Communicate findings clearly to technical and non-technical stakeholders, including concise briefings for leadership when needed.
Benefits
- OpenAI is an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic.
- Background checks for applicants will be administered in accordance with applicable law, and qualified applicants with arrest or conviction records will be considered for employment consistent with those laws, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act, for US-based candidates.
- We are committed to providing reasonable accommodations to applicants with disabilities, and requests can be made via this link.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
